Nodes/IAMCCS-nodes/MiniMax H3 Shotboard Settings → CineLinX
ComfyUI Node

MiniMax H3 Shotboard Settings → CineLinX

All the MiniMax H3 Shotboard settings, exported as one CineLinX config

By IAMCCS·Created 12 months ago·Updated 5 days ago· 115
MiniMax H3 Shotboard Settings → CineLinX
    • cine_linx
    ◄duration_seconds10.00►
    ◄frame_rate24►
    ◄guide_policyevery_checked_row►
    ◄min_guide_gap_seconds0.00►
    ◄max_guides50►
    ◄default_force1.00►
    ◄promptrelay_epsilon0.0010►
    ◄ltx_round_modenone►
    ◄width960►
    ◄height544►
    ◄image_width960►
    ◄image_height544►
    ◄image_resize_methodcrop►
    ◄image_multiple_of32►
    ◄img_compression0►
    ◄task_modeauto_from_timeline►
    ◄audio_modeh3_native_generated►
    ◄prompt_mappingglobal_plus_local►
    ◄performance_profilelow_vram_balanced►
    ◄text_encoder_devicegpu_auto►
    ◄seed42►
    ◄seed_control_after_generate_compatfixed►
    ◄seed_stride1►
    ◄steps16►
    ◄sampler_nameeuler►
    ◄schedulersimple►
    ◄denoise1.00►
    ◄shift_video12.00►
    ◄shift_audio3.00►
    ◄turbo_modeoff►
    ◄turbo_lora_name►
    ◄turbo_strength1.00►
    ◄turbo_sampler_modeaudio_fixed►
    ◄reference_resize_policyoff►
    ◄reference_resize_megapixels0.50►
    ◄reference_resize_filterarea►
    ◄accelerationlow_vram_auto►
    ◄ref_image_sizematch►
    ◄sol_conditioningexact_kv_and_rows►
    ◄spectrum_profilelow_vram►
    ◄vram_clean_before_decodetrue►
    ◄rife_modeoff►
    ◄reference_role_1subject_identity►
    ◄reference_role_2subject_identity►
    ◄reference_role_3composition►
    ◄reference_role_4style►
    ◄reference_video_roleoff►
    ◄reference_audio_roleoff►
    ◄voice_reference_picture_index0►
    ◄v2v_guide_moderaw_only►
    ◄v2v_source_range_policytimeline_segment►
    ◄v2v_source_offset_seconds0.00►
    ◄v2v_source_fitcanvas_pad►
    ◄v2v_source_end_policyhold_last_for_grid►
    ◄v2v_audio_pairingpair_with_source_video►
    ◄flf_join_modeh3_keyframe_cut►
    ◄flf_overlap_frames0►
    ◄flf_continuity_modestable_keyframes►
    ◄flf_continuity_tail_frames22►
    ◄flf_continuity_audiotrue►
    ◄upscale_modeoff►
    ◄upscale_enabledfalse►
    ◄upscale_width1920►
    ◄upscale_height1080►
    ◄upscale_prompt►
    ◄upscale_sagetrue►
    ◄upscale_seed_offset10000►
    ◄wan_upscale_denoise0.20►
    ◄ltx_seam_safetrue►
    ◄ltx_detailer_enabledfalse►
    ◄ltx_detailer_lora_name►
    ◄ltx_detailer_strength0.60►
    ◄ltx_4k_enabledfalse►
    ◄ltx_4k_qualityULTRA►
    ◄ltx_looper_temporal_tile_size80►
    ◄ltx_looper_temporal_overlap24►
    ◄ltx_looper_guiding_strength1.00►
    ◄ltx_looper_overlap_strength0.50►
    ◄ltx_looper_cond_image_strength1.00►
    ◄ltx_looper_horizontal_tiles1►
    ◄ltx_looper_vertical_tiles1►
    ◄ltx_looper_spatial_overlap1►
    ◄face_detailer_enabledfalse►
    ◄face_detailer_profilebalanced►
    ◄face_detailer_use_sam_maskfalse►
    ◄h3_upres_model_name►
    ◄h3_upres_precisionfp16►
    ◄h3_upres_devicecuda►
    ◄h3_upres_keep_models_residentfalse►
    ◄h3_upres_steps1►
    ◄h3_upres_denoise0.20►
    ◄h3_upres_samplersa_solver►
    ◄h3_upres_schedulersimple►
    ◄h3_upres_temporal_chunk85►
    ◄h3_upres_temporal_overlap17►
    ◄h3_upres_anchor_strength0.999►
    ◄h3_upres_tile_width864►
    ◄h3_upres_tile_height480►
    ◄h3_upres_overlap_width128►
    ◄h3_upres_overlap_height128►
    ◄h3_upres_fade_width32►
    ◄h3_upres_fade_height32►
    ◄h3_upres_min_tile_size256►
    ◄h3_upres_overlap_modeearlier►
    ◄h3_upres_overlap_blendlinear►
    ◄h3_upres_rtx_enabledfalse►
    ◄h3_upres_rtx_qualityULTRA►
    ◄h3_upres_pixel_groups1►
    ◄h3_upres_window_frames136►
    ◄h3_upres_window_overlap22►
    ◄h3_upres_pixel_methodrtx_vsr►
    ◄secondary_lora_enabledfalse►
    ◄secondary_lora_name►
    ◄secondary_lora_strength0.00►
    ◄motion_context_window_frames362►
    ◄h3_exact_profilertx_xx60_8_12gb_124►
    ◄h3_exact_chunk_rows2048►
    ◄h3_exact_precision_modePreserve native►
    ◄h3_exact_qkv_streamingAuto►
    ◄h3_exact_attention_memoryStandard►
    ◄h3_clipproj_profile4b_v3.1►
    ◄h3_clipproj_load_modedynamic►
    ◄h3_r40_seed_scout_enabledfalse►
    ◄h3_r40_candidate_count3►
    ◄h3_r40_seed_stride1000003►
    ◄h3_r40_preview_max_frames49►
    ◄h3_r40_sparse_enabledfalse►
    ◄h3_r40_sparse_video_budget0.30►
    ◄h3_r40_sparse_denser_edgestrue►
    ◄pdd_lora_name►
    ◄pdd_strength1.00►
    ◄h3_controlnet_enabledfalse►
    ◄h3_controlnet_name►
    ◄h3_controlnet_kindpose_dwpose►
    ◄h3_controlnet_strength1.00►
    ◄h3_controlnet_start_percent0.00►
    ◄h3_controlnet_end_percent1.00►
    ◄h3_controlnet_frame_scopetimeline_segment►
    ◄h3_controlnet_end_policystrict_match►
    ◄fused_turbo_model_name►
    ◄fused_turbo_sigma_preset4_step►
    ◄longvid_terminal_endpoint_modehard_image►
    ◄longvid_pianosequenza_2stage_enabledfalse►
    ◄longvid_pianosequenza_stage_count2_stage►
    ◄longvid_pianosequenza_split_modeauto►
    ◄longvid_pianosequenza_auto_profilebalanced►
    ◄longvid_pianosequenza_manual_stage1_steps4►
    ◄longvid_pianosequenza_manual_stage2_steps2►
    ◄longvid_pianosequenza_manual_stage3_steps1►
    ◄upscale_link_to_nativefalse►
    ◄upscale_link_factor640x384 -> 1280x768►
    ◄longvid_pianosequenza_stage_profile2_stage_full►
    ◄longvid_guide_window_policylegacy_auto►
    ◄h3_pixel_tiled_methodcpu_lanczos►
    ◄h3_pixel_tiled_model_name►
    ◄h3_pixel_tiled_tile_size512►
    ◄h3_pixel_tiled_overlap64►
    ◄h3_continuation_checkpoint►
    ◄h3_continuation_context_frames22►
    ◄h3_continuation_handover_modeterminal►
    ◄h3_continuation_manual_tail_frames0►
    ◄h3_refmod_enabledfalse►
    ◄h3_refmod_name►
    ◄h3_refmod_strength1.00►
    ◄h3_refmod_retention1.00►
    ◄h3_refmod_max_tokens0►
    ◄h3_continuation_enabledfalse►
    ◄h3_continuation_save_enabledfalse►
    ◄h3_faceswap_sam_model►
    ◄h3_faceswap_birefnet_model►
    ◄h3_faceswap_mask_prompthead►
    ◄h3_faceswap_threshold0.30►
    ◄h3_faceswap_objects►
    ◄h3_faceswap_cleanup_threshold0.30►
    ◄h3_faceswap_cleanup_shrink12►
    ◄h3_faceswap_cleanup_min_frames4►
    ◄h3_faceswap_cleanup_edge_grow16►
    ◄h3_faceswap_crop_scale1.75►
    ◄h3_faceswap_crop_megapixels0.50►
    ◄h3_faceswap_grow_spatial36►
    ◄h3_faceswap_grow_temporal1►
    ◄h3_faceswap_feather16►
    ◄h3_sla_sparsity0.85►
    ◄h3_sla_dense_last_steps0►
    ◄h3_advisor_state{}►
    ◄seed_policyfixed_per_generation►
    ◄keyframe_joint_latent_newfalse►
    ◄h3_continuation_visual_handoverauto_safe►
    ◄h3_continuation_run_and_gun_enabledtrue►
    ◄h3_continuation_run_and_gun_joinsoft_av►
    ◄h3_continuation_soft_video_frames4►
    ◄h3_continuation_soft_video_curvesmoothstep►
    ◄h3_continuation_soft_audio_ms15►
    ◄h3_faceswap_generate_new_audiofalse►

    The IAMCCS_MiniMaxH3ShotPlanner (the Shotboard) has so many widgets that splitting the config from the planning is the obvious quality-of-life move. IAMCCS_ShotboardH3Settings is that split: it's the same settings surface as the Shotboard - same contracts, same option lists - but its only job is to package them into one cine_linx output that the Shotboard (or another consumer) can read. You can't get a cleaner separation of "configure once" from "plan each shot."

    How it works

    Rather than maintaining a second fragile widget schema, the node literally borrows the Shotboard's input definitions (IAMCCS_MiniMaxH3ShotPlanner.INPUT_TYPES()), groups them by category, and re-exposes them with display names like 08 · ADVANCED COMPATIBILITY · ltx round mode. That means every future option the Shotboard gains - samplers, installed LoRAs, new presets - appears here automatically. It also strips the control_after_generate auto-seed behavior, because this is a persisted configuration source, not a sampler; the Shotboard keeps the single seed control.

    Practically, you get the full set of Shotboard knobs here: duration_seconds, width/height (and the image-reference variants image_width/image_height with their resize method), guide_policy, default_force, promptrelay_epsilon, ltx_round_mode, and the rest of the H3 settings groups. You set them once, wire the cine_linx output into the Shotboard's cine_linx input, and the shot inherits them.

    Outputs

    A single output: cine_linx, carrying the settings payload under an iamccs_minimax_h3_settings schema with schema_version: 1. The node's policy strings make the priority explicit: minimax_h3_settings_source: IAMCCS_ShotboardH3Settings and minimax_h3_settings_priority: external_cine_linx_over_local_snapshot - i.e. when both an external settings CineLinX and the Shotboard's own widgets are present, the external config wins. That's the whole contract in two lines: this node is meant to be the authority, so don't fight it by also hand-editing the same fields in the Shotboard.

    Why you'd bother

    Two workflows make it worth it. First, presets: build two or three of these as saved config sources (a "hero quality" one, a "low VRAM draft" one) and switch between them by rewiring a single connection instead of scrolling fifty widgets. Second, consistency across many shots: if you always render the same canvas size, guide policy and round mode, locking them here removes a whole class of "one segment rendered at the wrong resolution" accidents.

    Ships with IAMCCS-nodes: ComfyUI Manager → search "IAMCCS", or cd ComfyUI/custom_nodes && git clone https://github.com/IAMCCS/IAMCCS-nodes.git, then restart. No extra models or dependencies beyond the pack.

    CategoryIAMCCS/MiniMax H3/Settings

    Inputs (194)

    NameTypeDefaultDescription
    duration_secondsFLOAT10.000.01–36000—
    frame_rateINT2424–24—
    guide_policyCOMBOevery_checked_row1 options: every_checked_row
    min_guide_gap_secondsFLOAT0.000–0—
    max_guidesINT5050–50—
    default_forceFLOAT1.001–1—
    promptrelay_epsilonFLOAT0.00100.001–0.001—
    ltx_round_modeCOMBOnone1 options: none
    widthINT960256–5760—
    heightINT544256–5760—
    image_widthINT960256–5760—
    image_heightINT544256–5760—
    image_resize_methodCOMBOcrop5 options: crop, pad, keep proportion, stretch,
    image_multiple_ofINT3232–32—
    img_compressionINT00–100—
    task_modeCOMBOauto_from_timeline18 options: auto_from_timeline, t2va, i2va, fl2va, ref2va, v2va_controlnet, +12
    audio_modeCOMBOh3_native_generated4 options: h3_native_generated, h3_ref2va_audio, h3_custom_audio_drive, external_audio_post
    prompt_mappingCOMBOglobal_plus_local3 options: global_plus_local, local_only, global_only
    performance_profileCOMBOlow_vram_balanced14 options: rtx_xx60_safe, rtx_xx70_balanced, rtx_xx80_quality, rtx_xx90_max, low_vram_draft, low_vram_balanced, +8
    text_encoder_deviceCOMBOgpu_auto4 options: gpu_auto, cpu_direct, auto, cpu_safe_12gb
    seedINT420–18446744073709550000—
    seed_control_after_generate_compatSTRINGfixed—
    seed_strideINT10–18446744073709550000—
    stepsINT161–100—
    sampler_nameCOMBOeuler44 options: res_multistep, euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, +38
    schedulerCOMBOsimple9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3
    denoiseFLOAT1.000–1—
    shift_videoFLOAT12.000.01–100—
    shift_audioFLOAT3.000.01–100—
    turbo_modeCOMBOoff3 options: off, early_8_10, ckpt500_6_8
    turbo_lora_nameCOMBO1 options:
    turbo_strengthFLOAT1.000–4—
    turbo_sampler_modeCOMBOaudio_fixed2 options: audio_fixed, res_multistep_stock
    reference_resize_policyCOMBOoff4 options: canvas_crop, canvas_pad, total_pixels, off
    reference_resize_megapixelsFLOAT0.500.1–2—
    reference_resize_filterCOMBOarea4 options: area, bilinear, bicubic, nearest-exact
    accelerationCOMBOlow_vram_auto21 options: low_vram_auto, native, h3_sage, h3_sla, sol_low_vram, sol_adaptive_safe, +15
    ref_image_sizeCOMBOmatch2 options: match, max
    sol_conditioningCOMBOexact_kv_and_rows2 options: exact_kv_and_rows, exact_kv
    spectrum_profileCOMBOlow_vram5 options: low_vram, quality, aggressive, conservative_3060, conservative_quality
    vram_clean_before_decodeBOOLEANtrue—
    rife_modeCOMBOoff3 options: off, rife_48fps, rife_60fps
    reference_role_1COMBOsubject_identity5 options: subject_identity, keyframe, composition, style, disabled
    reference_role_2COMBOsubject_identity5 options: subject_identity, keyframe, composition, style, disabled
    reference_role_3COMBOcomposition5 options: subject_identity, keyframe, composition, style, disabled
    reference_role_4COMBOstyle5 options: subject_identity, keyframe, composition, style, disabled
    reference_video_roleCOMBOoff5 options: off, motion_camera, temporal_structure, video_edit, continuation
    reference_audio_roleCOMBOoff5 options: off, voice_timbre, rhythm_timing, audio_reuse, sound_reference
    voice_reference_picture_indexINT00–4—
    v2v_guide_modeCOMBOraw_only5 options: , raw_only, raw_pose, raw_depth, raw_depth_pose
    v2v_source_range_policyCOMBOtimeline_segment4 options: , timeline_segment, sequential_requested, repeat_from_offset
    v2v_source_offset_secondsFLOAT0.000–86400—
    v2v_source_fitCOMBOcanvas_pad5 options: , native_adapt, canvas_pad, canvas_crop, stretch
    v2v_source_end_policyCOMBOhold_last_for_gridHOLD LAST FOR GRID requires the complete visible source and freezes only H3's hidden 17k+5 tail (recommended). HOLD LAST VISIBLE also extends a genuinely short source with its final frame and silence; continuity survives but lip-sync cannot continue beyond the real source. ERROR requires real source frames even for the technical tail.
    v2v_audio_pairingCOMBOpair_with_source_video4 options: , pair_with_source_video, standalone_reference, off
    flf_join_modeCOMBOh3_keyframe_cut2 options: h3_keyframe_cut, wan_overlap_blend
    flf_overlap_framesINT00–24—
    flf_continuity_modeCOMBOstable_keyframes3 options: stable_keyframes, native_av_context, longvid_latent_tail_experimental
    flf_continuity_tail_framesCOMBO223 options: 22, 39, 56
    flf_continuity_audioBOOLEANtrue—
    upscale_modeCOMBOoff10 options: off, rtx_final, pixel_tiled_low_vram, h3_fast_latent_2pass, h3_pixel_refine, h3_ultimate_tiled, +4
    upscale_enabledBOOLEANfalse—
    upscale_widthINT1920256–7680—
    upscale_heightINT1080256–4320—
    upscale_promptSTRING—
    upscale_sageBOOLEANtrue—
    upscale_seed_offsetINT100000–18446744073709550000—
    wan_upscale_denoiseFLOAT0.200–1—
    ltx_seam_safeBOOLEANtrue—
    ltx_detailer_enabledBOOLEANfalse—
    ltx_detailer_lora_nameCOMBO1 options:
    ltx_detailer_strengthFLOAT0.600–2—
    ltx_4k_enabledBOOLEANfalse—
    ltx_4k_qualityCOMBOULTRA4 options: ULTRA, HIGH, MEDIUM, LOW
    ltx_looper_temporal_tile_sizeINT8024–1000—
    ltx_looper_temporal_overlapINT2416–80—
    ltx_looper_guiding_strengthFLOAT1.000–1—
    ltx_looper_overlap_strengthFLOAT0.500–1—
    ltx_looper_cond_image_strengthFLOAT1.000–1—
    ltx_looper_horizontal_tilesINT11–6—
    ltx_looper_vertical_tilesINT11–6—
    ltx_looper_spatial_overlapINT11–8—
    face_detailer_enabledBOOLEANfalse—
    face_detailer_profileCOMBObalanced5 options: balanced, small_faces, gentle, sam_face_mask, wide_character_12gb
    face_detailer_use_sam_maskBOOLEANfalse—
    h3_upres_model_nameCOMBOChoose an installed H3 3D latent upscaler. Auto uses an installed FP16 checkpoint first; no model is downloaded.
    h3_upres_precisionCOMBOfp163 options: fp16, bf16, fp32
    h3_upres_deviceCOMBOcuda2 options: cuda, cpu
    h3_upres_keep_models_residentBOOLEANfalse—
    h3_upres_stepsINT11–20—
    h3_upres_denoiseFLOAT0.200–1—
    h3_upres_samplerCOMBOsa_solver44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38
    h3_upres_schedulerCOMBOsimple9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3
    h3_upres_temporal_chunkINT8517–1700—
    h3_upres_temporal_overlapINT170–850—
    h3_upres_anchor_strengthFLOAT0.9990–1—
    h3_upres_tile_widthINT86432–4096—
    h3_upres_tile_heightINT48032–4096—
    h3_upres_overlap_widthINT1280–2048—
    h3_upres_overlap_heightINT1280–2048—
    h3_upres_fade_widthINT320–2048—
    h3_upres_fade_heightINT320–2048—
    h3_upres_min_tile_sizeINT2560–4096—
    h3_upres_overlap_modeCOMBOearlier2 options: earlier, later
    h3_upres_overlap_blendCOMBOlinear4 options: linear, smoothstep, overwrite, midpoint
    h3_upres_rtx_enabledBOOLEANfalse—
    h3_upres_rtx_qualityCOMBOULTRA4 options: ULTRA, HIGH, MEDIUM, LOW
    h3_upres_pixel_groupsINT11–16—
    h3_upres_window_framesINT13634–510—
    h3_upres_window_overlapINT220–170—
    h3_upres_pixel_methodCOMBOrtx_vsr4 options: rtx_vsr, lanczos-ish bicubic, bilinear, nearest-exact
    secondary_lora_enabledBOOLEANfalse—
    secondary_lora_nameCOMBO1 options:
    secondary_lora_strengthFLOAT0.00-2–2—
    motion_context_window_framesINT36256–362Maximum native H3 sample window including the carried AV tail. 362 restores the proven R37/R41/R42 contract. Smaller values are explicit memory trade-offs.
    h3_exact_profileCOMBOrtx_xx60_8_12gb_124Editable hardware-class baseline: xx60 124f/5.17s, xx70 209f/8.71s, xx80 294f/12.25s, xx90 362f/15.08s. It never overrides the visible window, memory, ClipProj or sampling boxes.
    h3_exact_chunk_rowsINT2048256–655362048 is the conservative 8–12 GB value. Larger values can be faster but use more activation memory.
    h3_exact_precision_modeCOMBOPreserve nativePreserve native keeps INT8/W4A8 checkpoints in their released precision without an implicit conversion.
    h3_exact_qkv_streamingCOMBOAutoAuto preserves the current dense attention backend and adds bounded Q/K/V carriers only where compatible.
    h3_exact_attention_memoryCOMBOStandardLower VRAM performs extra exact attention work. It is a safety fallback, not an approximate cache.
    h3_clipproj_profileCOMBO4b_v3.14B v3.1 is the default lower-memory conditioning encoder. 8B is larger and heavier. Off uses the connected workflow fallback CLIP. This choice does not replace the MiniMax H3 denoiser model.
    h3_clipproj_load_modeCOMBOdynamicDynamic uses ComfyUI-managed offload. Streaming lowers the peak further at a speed cost.
    h3_r40_seed_scout_enabledBOOLEANfalseCandidate-scout workflows only. Samples low-resolution candidates before one selected take enters delivery; ordinary generation workflows ignore this field.
    h3_r40_candidate_countINT31–41 keeps normal cost; 2-4 create independent cacheable seed candidates. Use 3 for hero-shot scouting, not for every automatic LongVid chunk.
    h3_r40_seed_strideINT10000031–18446744073709550000Candidate N uses base seed + N × stride. 1,000,003 provides widely separated deterministic candidates without a hidden prompt or model override.
    h3_r40_preview_max_framesINT491–209Limits each candidate preview batch only; it never shortens or changes the generated AV latent.
    h3_r40_sparse_enabledBOOLEANfalseOptional current H3SparseAttention. Faster/lower VRAM can change motion, detail or prompt adherence; Off is the quality-safe default.
    h3_r40_sparse_video_budgetFLOAT0.300.05–1Fraction of video KV attention retained. 1.0 is dense-equivalent routing; 0.30 is faster but is not lossless.
    h3_r40_sparse_denser_edgesBOOLEANtrueAdds attention budget to the first and last sampling steps to protect layout, prompt adherence and final detail.
    pdd_lora_nameCOMBOSelect a native Kijai *_Acc-8Step*_comfy LoRA from models/loras and match FL2VA/Ref2VA to the loaded trunk. Legacy aptech pdd_acc files require their companion loader and are rejected here.
    pdd_strengthFLOAT1.000–2Keep 1.0. Native shape-changing PDD head banks require full trained strength; any different visible Queue-truth value fails clearly instead of being silently replaced.
    h3_controlnet_enabledBOOLEANfalseOFF preserves the standard generation path exactly. ON requires a preprocessed control-video CineLinX module and an installed H3 Fun ControlNet.
    h3_controlnet_nameCOMBOSelect the MiniMax H3 Fun Union checkpoint from models/model_patches. Existing IAMCCS installs in models/controlnet remain compatible.
    h3_controlnet_kindCOMBOpose_dwposeDeclare the already-preprocessed input: DWPose, depth, Canny, HED, MLSD or inpaint. This does not run a hidden preprocessor.
    h3_controlnet_strengthFLOAT1.000–21.0 is the reference pose-control baseline. Lower values release structure; higher values can over-constrain identity and texture.
    h3_controlnet_start_percentFLOAT0.000–1Sampling interval start. 0.0 applies control from the first denoise step.
    h3_controlnet_end_percentFLOAT1.000–1Sampling interval end. 1.0 applies control throughout; earlier release can preserve more natural detail.
    h3_controlnet_frame_scopeCOMBOtimeline_segmentTimeline segment slices the full source by each Shotboard chunk start. Repeat each chunk restarts from source frame zero.
    h3_controlnet_end_policyCOMBOstrict_matchStrict match hard-fails before sampling if the source cannot cover the chunk. Hold last repeats the final control frame.
    fused_turbo_model_nameCOMBOSelect the installed MATLOWAI/Kijai fused MiniMax H3 INT8 ConvRot model from diffusion_models. This is a full model, not a LoRA, and is restricted to T2VA.
    fused_turbo_sigma_presetCOMBO4_step4, 6 or 8 exact manual-sigma steps. The Fast Preview button sets Euler, 12/3 shifts, denoise 1 and turns other acceleration LoRAs off.
    longvid_terminal_endpoint_modeCOMBOhard_imageHARD IMAGE = legacy exact final AddGuide. LATENT FREE CLOSURE = soft sampled-latent closure. PIANOSEQUENZA LINEAR = upstream-parity direct latent tail with static linear temporal release. PIANOSEQUENZA DRIFT = upstream-parity frozen prefix plus sigma-matched dynamic release. PIANOSEQUENZA NATIVE = upstream-parity native latent-tail keyframe on a fresh video target. PIANOSEQUENZA PHASE = upstream-parity phase-aligned direct latent step guides. PIANOSEQUENZA FROZEN = upstream-parity exact frozen tail as target prefix. PIANOSEQUENZA 2 STAGE = legacy serialized alias for the separate Multi-Stage Spatial toggle. PIANOSEQUENZA HD = self-contained two-stage 0.5x→1.0x progressive solve: every continuation chunk carries the previous native editorial tail, applies sigma-matched DRIFT on the protected prefix, solves LOW, performs the learned H3 latent lift, then completes the SAME sigma schedule at HIGH. The HD engine owns its two-stage contract; the separate Multi-Stage Spatial toggle is ignored while HD is selected. Existing Pianosequenza modes remain unchanged; IAMCCS AudioCon remains authoritative.
    longvid_pianosequenza_2stage_enabledBOOLEANfalseOFF is authoritative one-stage generation. ON enables the IAMCCS progressive spatial path and reveals one Stage Profile dropdown for 2-stage/3-stage and safe/full behaviour. Legacy endpoint value pianosequenza_2stage is migrated to DRIFT but cannot override an explicit OFF toggle.
    longvid_pianosequenza_stage_countCOMBO2_stage2_STAGE = classic low→high progressive path. 3_STAGE = low→mid→high progressive spatial solve.
    longvid_pianosequenza_split_modeCOMBOautoAUTO dynamically allocates LOW/MID/HIGH denoising steps from the total schedule. Manual uses the explicit stage step fields below.
    longvid_pianosequenza_auto_profileCOMBObalancedBALANCED ≈ 75/25 total distribution. LOW_AUTHORITY keeps more steps in LOW. HIGH_REFINE gives more to later stages. FAST_SAFE is conservative on high-res. PDD_SAFE and TOETAO_SAFE are tuned for compact step budgets.
    longvid_pianosequenza_manual_stage1_stepsINT40–64Manual split only. Stage 1 = LOW-resolution denoising steps.
    longvid_pianosequenza_manual_stage2_stepsINT20–64Manual split only. In 2-stage this is HIGH. In 3-stage this is MID.
    longvid_pianosequenza_manual_stage3_stepsINT10–64Manual split only. Used only when spatial stage count is 3_STAGE (final HIGH stage).
    upscale_link_to_nativeBOOLEANfalsePianosequenza multi-stage only. ON makes the selected legal pair authoritative: the first stage starts at LOW and the same LongVid sample finishes at HIGH. Default pair is 640x384 → 1280x768. It does not enable post-delivery upscale.
    upscale_link_factorCOMBO640x384 -> 1280x768Linked LOW → HIGH generation pair. 640x384 → 1280x768 is the default. Legacy 2x/3x/4x saved values are accepted and normalized to the default pair.
    longvid_pianosequenza_stage_profileCOMBO2_stage_full2 STAGE FULL = LOW H3 → learned lift → HIGH H3 refine. 2 STAGE SAFE DELIVERY = LOW H3 through the full sigma schedule → learned lift to HIGH, no high-resolution H3 forward. 3 STAGE SAFE MID = LOW H3 → MID H3 → learned lift to HIGH, no final HIGH H3 forward. 3 STAGE FULL = LOW H3 → MID H3 → HIGH H3.
    longvid_guide_window_policyCOMBOlegacy_autoLEGACY AUTO preserves existing saves: the old latent-tail continuity selection enables Adaptive windows. STANDARD POSITIONED uses ordinary H3 technical windows with positioned guides and no hidden latent-prefix carry (362f is the normal macro recipe). ADAPTIVE LATENT TAIL enables the narrow high-resolution 209/124-style windows with the configured latent tail.
    h3_pixel_tiled_methodCOMBOcpu_lanczos2 options: cpu_lanczos, model_tiled
    h3_pixel_tiled_model_nameCOMBO1 options:
    h3_pixel_tiled_tile_sizeINT512128–2048—
    h3_pixel_tiled_overlapINT640–512—
    h3_continuation_checkpointSTRING—
    h3_continuation_context_framesCOMBO223 options: 5, 22, 39
    h3_continuation_handover_modeCOMBOterminalTERMINAL = continue from the actual final AV latent boundary (recommended). AUTO = use saved freeze/lock analysis. MANUAL = deliberately ignore N final source frames.
    h3_continuation_manual_tail_framesINT00–3400—
    h3_refmod_enabledBOOLEANfalseOff preserves the exact former H3 conditioning. On injects one saved provider RefMod into every selected H3 chunk before sampling.
    h3_refmod_nameSTRINGRelative name under models/refmods, without .safetensors. Select from the PRO library or type the provider name.
    h3_refmod_strengthFLOAT1.000–1—
    h3_refmod_retentionFLOAT1.000–1—
    h3_refmod_max_tokensINT00–1048576—
    h3_continuation_enabledBOOLEANfalseOpt-in. Only the first queued Shotboard chunk starts from the selected external AV checkpoint; later chunks keep their own selected mode.
    h3_continuation_save_enabledBOOLEANfalseOpt-in export contract for a terminal sampled AV latent. It does not activate loading.
    h3_faceswap_sam_modeloptCOMBOInstalled SAM3 multiplex checkpoint. Required only when no source mask is connected.
    h3_faceswap_birefnet_modeloptCOMBOBiRefNet model used by FACE SWAP v1 to place both identity views on white before stitching them.
    h3_faceswap_mask_promptoptSTRINGheadTracked identity region. Keep head for hair, ears, jaw and profile stability.
    h3_faceswap_thresholdoptFLOAT0.300–1Foxydits reference threshold for stable single-subject SAM3 tracking.
    h3_faceswap_objectsoptSTRINGLeave empty for one subject. For multi-person footage, enter the intended tracked-object index explicitly.
    h3_faceswap_cleanup_thresholdoptFLOAT0.300–1—
    h3_faceswap_cleanup_shrinkoptINT121–128—
    h3_faceswap_cleanup_min_framesoptINT41–64—
    h3_faceswap_cleanup_edge_growoptINT160–128—
    h3_faceswap_crop_scaleoptFLOAT1.751–4—
    h3_faceswap_crop_megapixelsoptFLOAT0.500–4Minimum crop sampling area; 0 preserves the tracked crop size. Editable workload, not a GPU guarantee.
    h3_faceswap_grow_spatialoptINT360–256—
    h3_faceswap_grow_temporaloptINT10–64—
    h3_faceswap_featheroptINT160–256—
    h3_sla_sparsityoptFLOAT0.850–0.95SLA attention only: fraction of key blocks skipped. LightX2V Turbo SLA training recipe uses 0.85.
    h3_sla_dense_last_stepsoptINT00–20SLA attention only: optional final dense steps for an explicit quality comparison.
    h3_advisor_stateoptSTRING{}Per-mode local advisor state. Proposals apply only after acceptance.
    seed_policyoptCOMBOfixed_per_generationFixed/random per generation: one seed for all chunks. Fixed per chunk: base + index × stride. Random per chunk: independent seeds derived from the randomized queue seed. Random policies choose a new base when you press Queue in Settings Pro; API clients must supply their base seed.
    keyframe_joint_latent_newoptBOOLEANfalseKeyframe Joint only: chain original generated AV latent tails through the LatentGoAhead branch. Destination images remain guides. OFF keeps one joint sample.
    h3_continuation_visual_handoveroptCOMBOauto_safeAUTO SAFE: if Shotboard first/last are the same still, use it only as a Qwen identity reference and let saved AV own the temporal opening; a distinct last image remains a future destination. LATENT ONLY: saved AV + prompt only. SHOTBOARD DESTINATION: legacy behavior, explicitly force the board endpoint.
    h3_continuation_run_and_gun_enabledoptBOOLEANtrueWhen continuing from a checkpoint with IAMCCS chain metadata, also build one cumulative A+B(+C...) master from the original segment files. Individual segment files stay available for the Video Editor.
    h3_continuation_run_and_gun_joinoptCOMBOsoft_avSOFT AV (recommended) uses the incoming generation's hidden, time-corresponding AV context to soften the outgoing boundary without changing latent continuation or programme duration. DIRECT preserves the exact hard join.
    h3_continuation_soft_video_framesoptINT40–16Recommended: 4. Delivery-only context-aligned blend; 0 disables video blending.
    h3_continuation_soft_video_curveoptCOMBOsmoothstepSMOOTHSTEP is the recommended short dissolve. LINEAR is available for a strictly uniform ramp.
    h3_continuation_soft_audio_msoptFLOAT150–100Recommended: 15 ms equal-power de-click against the matching hidden audio context. Keep it short for dialogue and lipsync.
    h3_faceswap_generate_new_audiooptBOOLEANfalseOFF (recommended): use source_video audio as Ref2VA lip timing and preserve that exact audio in the output. ON: ignore source audio for conditioning/output and generate a new native H3 audio stream.

    Outputs (1)

    NameTypeDescription
    cine_linxIAMCCS_SUPERNODE_LINX—